Stealing Your Android Patterns via Acoustic Signals

Zhou, Man; Wang, Qian; Yang, Jingxiao; Li, Qi; Jiang, Peipei; Chen, Yanjiao; Wang, Zhen

doi:10.1109/tmc.2019.2960778

Cited by 23 publications

(8 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, the attacker cannot bypass our liveness detection by replaying pre-recorded audio that was collected during previous rounds of detection. Note that, most people cannot hear the tone whose frequency is higher than 18KHz [47] and the performance of acoustic components in some smartphones decreases significantly when the frequency is higher than 21KHz [48]. Thus, we set f i in the range of 18 ∼ 21KHz.…”

Section: Audio Capturingmentioning

confidence: 99%

Securing Face Liveness Detection Using Unforgeable Lip Motion Patterns

Zhou,

Wang,

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Face authentication usually utilizes deep learning models to verify users with high recognition accuracy. However, face authentication systems are vulnerable to various attacks that cheat the models by manipulating the digital counterparts of human faces. So far, lots of liveness detection schemes have been developed to prevent such attacks. Unfortunately, the attacker can still bypass these schemes by constructing wide-ranging sophisticated attacks. We study the security of existing face authentication services (e.g., Microsoft, Amazon, and Face++) and typical liveness detection approaches. Particularly, we develop a new type of attack, i.e., the low-cost 3D projection attack that projects manipulated face videos on a 3D face model, which can easily evade these face authentication services and liveness detection approaches. To this end, we propose FaceLip, a novel liveness detection scheme for face authentication, which utilizes unforgeable lip motion patterns built upon well-designed acoustic signals to enable a strong security guarantee. The unique lip motion patterns for each user are unforgeable because FaceLip verifies the patterns by capturing and analyzing the acoustic signals that are dynamically generated according to random challenges, which ensures that our signals for liveness detection cannot be manipulated. Specially, we develop robust algorithms for FaceLip to eliminate the impact of noisy signals in the environment and thus can accurately infer the lip motions at larger distances. We prototype FaceLip on off-the-shelf smartphones and conduct extensive experiments under different settings. Our evaluation with 44 participants validates the effectiveness and robustness of FaceLip.

show abstract

Section: Audio Capturingmentioning

confidence: 99%

Securing Face Liveness Detection Using Unforgeable Lip Motion Patterns

Zhou,

Wang,

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…When the display technology was improved, some researchers also aimed at monitoring video displays by both electromagnetic and optical emanations [22][23][24]. The latest research can even eavesdrop from a cell phone screen or from tablet screen [25][26][27][28]. The work presented in [25], the authors presents a side-channel attack to retrieve PIN from a cell phone screen.…”

Section: Emission Security and Side-channel Analysismentioning

confidence: 99%

“…The authors report that to successfully infer the character or digit tap information, the distance between the victim and adversary needs to be less than 60 cm. However, in [27], the authors present acoustic side-channel attack to retrieve the lock patters by using the mic embedded in an android cell phones. The authors use a cellphone application to record the emanations of lock pattern and used to noise rejection filter, signal segmentation, relative movement measurement to infer the pattern of the fingertips.…”

Section: Emission Security and Side-channel Analysismentioning

confidence: 99%

Behavioral Acoustic Emanations: Attack and Verification of PIN Entry Using Keypress Sounds

Panda

Liu

Hancke

et al. 2020

Sensors

View full text Add to dashboard Cite

This paper explores the security vulnerability of Personal Identification Number (PIN) or numeric passwords. Entry Device (PEDs) that use small strings of data (PINs, keys or passwords) as means of verifying the legitimacy of a user. Today, PEDs are commonly used by personnel in different industrial and consumer electronic applications, such as entry at security checkpoints, ATMs and customer kiosks, etc. In this paper, we propose a side-channel attack on a 4–6 digit random PIN key, and a PIN key user verification method. The intervals between two keystrokes are extracted from the acoustic emanation and used as features to train machine-learning models. The attack model has a 60% chance to recover the PIN key. The verification model has an 88% accuracy on identifying the user. Our attack methods can perform key recovery by using the acoustic side-channel at low cost. As a countermeasure, our verification method can improve the security of PIN entry devices.

show abstract

“…Consequently, it is conceivable that such unauthorized audio recording can be used to recover sensitive user information, using inter-keystroke timing or statistical analysis to recover typed text [7] or even ten-character passwords within 20 attempts [8]. While some practitioners may dismiss the use of acoustic signals as a possible security loophole on mobile devices [9], recent publications [10][11][12][13][14] show that acoustic techniques such as tracking the Doppler effect, supplying an external excitation signal and Time Difference of Arrival (TDOA) that can be used to retrieve text input on physical keyboard can be adapted to compromise mobile devices as well. One such system, SonarSnoop utilises an active acoustic technique by emitting human inaudible acoustic signals and recording the echo to profile user interaction and infer touchscreen unlock patterns [14].…”

Section: Introductionmentioning

confidence: 99%

Categorizing Touch-Input Locations from Touchscreen Device Interfaces via On-Board Mechano-Acoustic Transducers

et al. 2021

View full text Add to dashboard Cite

Many mobile electronics devices, including smartphones and tablets, require the user to interact physically with the device via tapping the touchscreen. Conveniently, these compact devices are also equipped with high-precision transducers such as accelerometers and microphones, integrated mechanically and designed on-board to support a range of user functionalities. However, unintended access to these transducer signals (bypassing normal on-board data access controls) may allow sensitive user interaction information to be detected and thereby exploited. In this study, we show that acoustic features extracted from the on-board microphone signals, supported with accelerometer and gyroscope signals, may be used together with machine learning techniques to successfully determine the user’s touch input location on a touchscreen: our ensemble model, namely the random forest model, predicts touch input location with up to 86% accuracy in a realistic scenario. Accordingly, we present the approach and techniques used, the performance of the model developed, and also discuss limitations and possible mitigation methods to thwart possible exploitation of such unintended signal channels.

show abstract

Stealing Your Android Patterns via Acoustic Signals

Cited by 23 publications

References 40 publications

Securing Face Liveness Detection Using Unforgeable Lip Motion Patterns

Securing Face Liveness Detection Using Unforgeable Lip Motion Patterns

Behavioral Acoustic Emanations: Attack and Verification of PIN Entry Using Keypress Sounds

Categorizing Touch-Input Locations from Touchscreen Device Interfaces via On-Board Mechano-Acoustic Transducers

Contact Info

Product

Resources

About